Python SDK

pip install nolano

pip install git+https://github.com/tejasvaidhyadev/nolano.git

from nolano import Nolano

client = Nolano(api_key="your-api-key-here")

from nolano import Nolano
import pandas as pd

# Initialize the client
client = Nolano(api_key="your_api_key_here")

# Or set environment variable: NOLANO_API_KEY=your_api_key_here
client = Nolano()

# Verify API key (recommended)
verification = client.verify_api_key()
if not verification['valid']:
    print(f"API key issue: {verification['message']}")
    exit(1)

print("✅ API key verified successfully!")

# Prepare your time series data
df = pd.DataFrame({
    'date': pd.date_range(start='2023-01-01', periods=100, freq='D'),
    'sales': [100, 102, 98, 105, 110, 108, 115, 120, 125, 130, 128, 135, 140, 145, 150, 155, 160, 165, 170, 175, 180, 185, 190, 195, 200, 205, 210, 215, 220, 225, 230, 235, 240, 245, 250, 255, 260, 265, 270, 275, 280, 285, 290, 295, 300, 305, 310, 315, 320, 325, 330, 335, 340, 345, 350, 355, 360, 365, 370, 375, 380, 385, 390, 395, 400, 405, 410, 415, 420, 425, 430, 435, 440, 445, 450, 455, 460, 465, 470, 475, 480, 485, 490, 495, 500, 505, 510, 515, 520, 525, 530, 535, 540, 545, 550, 555, 560, 565, 570, 575]
})

# Generate forecast
forecast = client.forecast(
    dataset=df,
    target_col='sales',
    timestamp_col='date',
    forecast_horizon=30,
    data_frequency='Daily'
)

print(f"Forecast: {forecast.median}")
print(f"Lower bound: {forecast.lower_bound}")
print(f"Upper bound: {forecast.upper_bound}")

class Nolano:
    def __init__(
        self,
        api_key: str = None,
        model_id: str = "forecast-model-1"
    ):
        """
        Initialize the Nolano client.
        
        Args:
            api_key: Your Nolano API key (optional if NOLANO_API_KEY env var is set)
            model_id: Default model to use for forecasting
        """

def forecast(
    self,
    dataset: pd.DataFrame,
    target_col: str,
    timestamp_col: str,
    forecast_horizon: int,
    data_frequency: str = "Daily",
    forecast_frequency: str = None,
    confidence: float = 0.95,
    model_id: str = None
) -> NolanoForecast:
    """
    Generate time series forecasts from a pandas DataFrame.
    
    Args:
        dataset: pandas DataFrame with time series data
        target_col: Column name containing values to forecast
        timestamp_col: Column name containing timestamps
        forecast_horizon: Number of periods to forecast
        data_frequency: Data frequency (Daily, Hourly, Weekly, etc.)
        forecast_frequency: Forecast frequency (optional, defaults to data_frequency)
        confidence: Confidence level for prediction intervals
        model_id: Model to use (optional, uses default)
    
    Returns:
        NolanoForecast object with prediction data
    """

# Verify API key before making requests
try:
    result = client.verify_api_key()
    if not result['valid']:
        print(f"API key verification failed: {result['message']}")
        # Handle invalid API key case
        exit(1)
    
    print("API key verified successfully!")
    
    # Proceed with forecasting
    forecast = client.forecast(
        dataset=df,
        target_col='sales',
        timestamp_col='date',
        forecast_horizon=30,
        data_frequency='Daily'
    )
    
except ValueError as e:
    print(f"Parameter error: {e}")
except KeyError as e:
    print(f"Column not found: {e}")
except Exception as e:
    print(f"API error: {e}")

# List available models
models = client.list_models()
for model in models:
    print(model)

# Use a specific model
forecast = client.forecast(
    dataset=df,
    target_col='sales',
    timestamp_col='date',
    forecast_horizon=30,
    data_frequency='Daily',
    model_id='forecast-model-2'  # Use alternative model
)

# Validate your data before forecasting
validation = client.validate_data(
    dataset=df,
    target_col='sales',
    timestamp_col='date'
)

if validation['valid']:
    print("Data is valid!")
    print(f"Stats: {validation['stats']}")
else:
    print("Data issues found:")
    for warning in validation['warnings']:
        print(f"- {warning}")

# Access forecast data
forecast.forecast_timestamps  # List of forecast timestamp strings
forecast.median              # List of median forecast values
forecast.lower_bound         # List of lower confidence bound values
forecast.upper_bound         # List of upper confidence bound values

# Convert to DataFrame
df = forecast.to_dataframe()

# Evaluate forecast accuracy
actual_values = [105, 110, 108, 115, 120]  # Actual values for forecast period
metrics = forecast.evaluate(actual_values)
print(f"MAE: {metrics['mae']:.2f}")
print(f"WAPE: {metrics['wape']:.2f}%")

import os

# Set your API key
export NOLANO_API_KEY=your_api_key_here

# In your code
client = Nolano()  # Will automatically use NOLANO_API_KEY environment variable

from nolano import Nolano

client = Nolano()
result = client.verify_api_key()

if result['valid']:
    print("✅ API key is valid!")
else:
    print(f"❌ Issue: {result['message']}")